MCAP is a modular, performant, and serialization-agnostic container file format, useful for pub/sub and robotics applications.

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Segments.ai Python SDK

A cross platform app for quick and easy still image camera matching

Official fSpy importer for Blender

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series

All the handwritten notes 📝 and source code files 🖥️ used in my YouTube Videos on Machine Learning & Simulation (https://www.youtube.com/channel/UCh0P7KwJhuQ4vrzc3IRuw4Q)

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

C++ Implementation of PyTorch Tutorials for Everyone

lidar to camera projection of KITTI

Python client for iNaturalist

Learn make by example

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

Build and run Docker containers leveraging NVIDIA GPUs

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

Inspirational Mapping

Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Training materials associated with NVIDIA's CUDA Training Series (www.olcf.ornl.gov/cuda-training-series/)

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Open standard for machine learning interoperability

Visualizer for neural network, deep learning and machine learning models

A Simple PointPillars PyTorch Implementation for 3D LiDAR(KITTI) Detection.

A new markup-based typesetting system that is powerful and easy to learn.

Open3D: A Modern Library for 3D Data Processing

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

PyTorch implementation of Pointnet2/Pointnet++

match command-line arguments to their help text